>> There's not currently a mechanism for adding (or specifying, or changing) >> context. If this is important to you, please let us know via email to >> "[email protected]".
So is the entire worksheet sent, the line the cursor is on, or the selected text? > For some cases my description has taken multiple paragraphs, and often the > first answer misses something so I refer back or re-state and query again. It would be amazing to be able to play with the entire context. Several months ago when I was playing with AI a lot, I found one app that allowed me to "fix" the AI response by editing it and then sending the "fixed" response with my new question. With the censored AI models, this often allowed me to bypass the censorship by removing the "As an AI language model..." text and replacing it with the actual answer. This fooled the AI into continuing to talk about building bombs. Of course, I only did this to see if I could because I could just Google how to build a bomb if I really wanted to. But my point is that being able to edit the full context is useful. In fact, this could be a powerhouse AI tool if worked with local open source AI models and could be configured with chat templates (see https://docs.mistral.ai/models/). For example, that link shows that Mistral's chat template is as follows (I'm not even sure how to use this template, I just know this is Mistral's). ``` <s>[INST] Instruction [/INST] Model answer</s>[INST] Follow-up instruction [/INST] ``` Obviously, as a text editor, BBEdit wouldn't do anything other than put that text in the window so that the user could then edit it how they wanted. I'm not sure that this is really a path that should be pursued though because they're starting to make mixed AI models that can do audio, images, and text and I don't see how BBEdit would do audio (images are just paths to the files). I guess as just a text editor it would be nice to have a local copy of the chats rather than having them all stored on OpenAI's server or having them be ephemeral, which is the case when using AI cli apps. Which also makes me think that if you're going to support local AI models you might want to have more preferences than just the url to the API. You might want to run them from a cli tool like llama.cpp or ollama, which would mean you'd need to be able to change the cli flags passed to the tools. This is probably a good reason to not support local AI models or anything via cli since it just means bloat and losing focus. James Reynolds -- This is the BBEdit Talk public discussion group. If you have a feature request or need technical support, please email "[email protected]" rather than posting here. Follow @bbedit on Twitter: <https://twitter.com/bbedit> --- You received this message because you are subscribed to the Google Groups "BBEdit Talk" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/bbedit/100642D3-E07F-42F6-A347-F89EED6D8FBE%40gmail.com.
